Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Integrate Graph Architecture with rest of codebase #9803

Merged
merged 121 commits into from
Oct 14, 2021

Conversation

wochinge
Copy link
Contributor

@wochinge wochinge commented Oct 6, 2021

Proposed changes:

Open Issues

Status (please check what you already did):

  • added some tests for the functionality
  • updated the documentation
  • updated the changelog (please check changelog for instructions)
  • reformat files using black (please check Readme for instructions)

@wochinge
Copy link
Contributor Author

Some model regression tests were failing over night due to poetry issues. As we have also seen no changes in previous runs and the entity testing works now, I just give it one final run on the Sara dataset before merging @joejuzl @ka-bu

@github-actions
Copy link
Contributor

Commit: acd4601, The full report is available as an artifact.

Dataset: Sara, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 4m21s, train: 7m3s, total: 11m23s
0.7179 (0.00) 0.7949 (0.00) 0.7898 (0.00)
BERT + DIET(seq) + ResponseSelector(t2t)
test: 4m46s, train: 5m29s, total: 10m14s
0.7136 (0.00) 0.7925 (0.00) 0.7767 (0.00)
Sparse + BERT + DIET(bow) + ResponseSelector(bow)
test: 4m33s, train: 10m15s, total: 14m47s
0.6953 (0.00) 0.7949 (0.00) 0.8140 (0.00)
Sparse + BERT + DIET(seq) + ResponseSelector(t2t)
test: 4m58s, train: 7m49s, total: 12m46s
0.7020 (0.00) 0.7918 (0.00) 0.7922 (0.00)
Sparse + DIET(bow) + ResponseSelector(bow)
test: 1m38s, train: 6m44s, total: 8m21s
0.6654 (0.00) 0.7949 (0.00) 0.7814 (0.00)
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 2m3s, train: 5m26s, total: 7m29s
0.6822 (0.00) 0.7812 (0.00) 0.7851 (0.00)
Dialog Policy Configuration Action Level Micro Avg. F1 Conversation Level Accuracy Run Time Train Run Time Test
Rules 0.1266 (0.00) 0.0000 (0.00) 2m22s 1m16s
Rules + AugMemo 0.9149 (-0.01) 0.6301 (-0.03) 2m24s 1m30s
Rules + AugMemo + TED 0.9728 (-0.00) 0.7603 (0.00) 12m17s 2m58s
Rules + Memo 0.3860 (0.00) 0.1438 (0.00) 2m23s 1m22s
Rules + Memo + TED 0.9575 (0.00) 0.6678 (-0.00) 12m14s 2m50s
Rules + TED 0.9566 (0.00) 0.6541 (0.00) 12m16s 2m48s

@github-actions
Copy link
Contributor

Commit: df44e56, The full report is available as an artifact.

Dataset: Carbon Bot, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m31s, train: 5m23s, total: 6m54s
0.7942 (0.00) 0.4235 (0.00) 0.5382 (0.00)
BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m53s, train: 4m47s, total: 6m40s
0.8078 (0.00) 0.7787 (0.00) 0.5430 (0.00)
Sparse + BERT + DIET(bow) + ResponseSelector(bow)
test: 1m39s, train: 5m23s, total: 7m2s
0.7922 (0.00) 0.4235 (0.00) 0.5497 (0.00)
Sparse + BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m1s, train: 5m35s, total: 7m36s
0.7806 (0.00) 0.7880 (0.00) 0.5629 (0.00)
Sparse + DIET(bow) + ResponseSelector(bow)
test: 46s, train: 3m2s, total: 3m47s
0.7456 (0.00) 0.4235 (0.00) 0.4901 (0.00)
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 1m9s, train: 4m26s, total: 5m34s
0.7398 (0.00) 0.7022 (0.00) 0.5166 (0.00)

@koernerfelicia
Copy link
Contributor

Run when compared to # 134 (last fully successful model reg. test) https://github.com/RasaHQ/rasa/actions/runs/1111032086

Dataset: Carbon Bot, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m28s, train: 4m12s, total: 5m40s
0.7942 (0.00) 0.4235 (-0.33) 0.5382 (0.00)
BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m41s, train: 4m19s, total: 5m59s
0.8078 (0.01) 0.7787 (0.00) 0.5430 (0.00)
Sparse + BERT + DIET(bow) + ResponseSelector(bow)
test: 1m31s, train: 4m54s, total: 6m24s
0.7689 (-0.01) 0.4235 (-0.33) 0.5497 (-0.01)
Sparse + BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m48s, train: 5m8s, total: 6m55s
0.7806 (0.00) 0.7880 (-0.01) 0.5497 (-0.03)
Sparse + DIET(bow) + ResponseSelector(bow)
test: 44s, train: 2m50s, total: 3m34s
0.7398 (-0.00) 0.4235 (-0.33) 0.5249 (-0.01)
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 1m3s, train: 4m9s, total: 5m11s
0.7398 (0.00) 0.7022 (0.02) 0.5497 (0.01)

Dataset: Hermit, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 2m30s, train: 21m21s, total: 23m51s
0.8978 (0.00) 0.7504 (0.00) no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m46s, train: 15m1s, total: 17m47s
0.8913 (-0.00) 0.8049 (-0.00) no data
Sparse + BERT + DIET(bow) + ResponseSelector(bow)
test: 2m40s, train: 26m49s, total: 29m28s
0.8699 (0.00) 0.7504 (0.00) no data
Sparse + BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m56s, train: 19m0s, total: 21m56s
0.8727 (0.00) 0.7994 (0.00) no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 1m6s, train: 21m14s, total: 22m19s
0.8336 (0.00) 0.7504 (0.00) no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 1m21s, train: 14m38s, total: 15m58s
0.8355 (0.00) 0.7561 (0.00) no data

Dataset: Private 1, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m49s, train: 4m1s, total: 5m49s
0.9096 (0.00) 0.9612 (0.00) no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m10s, train: 3m46s, total: 5m56s
0.9148 (0.00) 0.9717 (0.00) no data
Spacy + DIET(bow) + ResponseSelector(bow)
test: 34s, train: 3m2s, total: 3m35s
0.8420 (0.00) 0.9574 (0.00) no data
Spacy + DIET(seq) + ResponseSelector(t2t)
test: 53s, train: 3m25s, total: 4m17s
0.8534 (-0.00) 0.9444 (0.00) no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 29s, train: 3m37s, total: 4m6s
0.8929 (-0.01) 0.9612 (0.00) no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 48s, train: 3m32s, total: 4m20s
0.9085 (0.01) 0.9735 (0.00) no data
Sparse + Spacy + DIET(bow) + ResponseSelector(bow)
test: 38s, train: 4m34s, total: 5m11s
0.8960 (0.01) 0.9574 (0.00) no data
Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)
test: 57s, train: 4m21s, total: 5m18s
0.8929 (-0.00) 0.9700 (0.00) no data

Dataset: Private 2, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m50s, train: 11m17s, total: 13m7s
0.8745 (0.00) no data no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m5s, train: 6m18s, total: 8m23s
0.8830 (0.00) no data no data
Spacy + DIET(bow) + ResponseSelector(bow)
test: 38s, train: 5m59s, total: 6m36s
0.7253 (0.00) no data no data
Spacy + DIET(seq) + ResponseSelector(t2t)
test: 47s, train: 6m0s, total: 6m47s
0.7822 (0.00) no data no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 37s, train: 5m41s, total: 6m18s
0.8498 (-0.01) no data no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 44s, train: 5m40s, total: 6m24s
0.8530 (0.00) no data no data
Sparse + Spacy + DIET(bow) + ResponseSelector(bow)
test: 48s, train: 8m35s, total: 9m23s
0.8594 (0.00) no data no data
Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)
test: 52s, train: 7m16s, total: 8m8s
0.8509 (0.00) no data no data

Dataset: Private 3, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 59s, train: 1m10s, total: 2m8s
0.9177 (0.00) no data no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m4s, train: 52s, total: 1m55s
0.8436 (0.00) no data no data
Spacy + DIET(bow) + ResponseSelector(bow)
test: 36s, train: 54s, total: 1m30s
0.6132 (0.00) no data no data
Spacy + DIET(seq) + ResponseSelector(t2t)
test: 42s, train: 44s, total: 1m25s
0.6255 (0.00) no data no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 33s, train: 1m6s, total: 1m38s
0.8683 (0.00) no data no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 37s, train: 49s, total: 1m25s
0.8642 (0.00) no data no data
Sparse + Spacy + DIET(bow) + ResponseSelector(bow)
test: 37s, train: 1m18s, total: 1m55s
0.8436 (-0.00) no data no data
Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)
test: 43s, train: 58s, total: 1m40s
0.8601 (0.00) no data no data

Dataset: Sara, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Dialog Policy Configuration Action Level Micro Avg. F1 Conversation Level Accuracy Run Time Train Run Time Test
Rules 0.1266 (0.00) 0.0000 (0.00) 2m34s 1m24s
Rules + AugMemo 0.9149 (-0.01) 0.6301 (-0.03) 2m30s 1m33s
Rules + AugMemo + TED 0.9727 (-0.00) 0.7534 (0.00) 13m8s 3m6s
Rules + Memo 0.3860 (0.00) 0.1438 (0.00) 2m34s 1m27s
Rules + Memo + TED 0.9555 (-0.00) 0.6644 (0.00) 13m2s 3m5s

@koernerfelicia
Copy link
Contributor

Run when compared to TF 2.6 (note 11% drop for Rules+Memo for Sara is not explained yet, ignore this)

Dataset: Carbon Bot, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m28s, train: 4m12s, total: 5m40s
0.7942 (0.00) 0.4235 (-0.33) 0.5382 (0.00)
BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m41s, train: 4m19s, total: 5m59s
0.8078 (0.01) 0.7787 (0.00) 0.5430 (0.01)
Sparse + BERT + DIET(bow) + ResponseSelector(bow)
test: 1m31s, train: 4m54s, total: 6m24s
0.7689 (-0.03) 0.4235 (-0.33) 0.5497 (-0.01)
Sparse + BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m48s, train: 5m8s, total: 6m55s
0.7806 (0.00) 0.7880 (-0.01) 0.5497 (-0.03)
Sparse + DIET(bow) + ResponseSelector(bow)
test: 44s, train: 2m50s, total: 3m34s
0.7398 (-0.01) 0.4235 (-0.33) 0.5249 (-0.01)
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 1m3s, train: 4m9s, total: 5m11s
0.7398 (0.00) 0.7022 (0.02) 0.5497 (0.01)

Dataset: Hermit, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 2m30s, train: 21m21s, total: 23m51s
0.8978 (-0.00) 0.7504 (0.00) no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m46s, train: 15m1s, total: 17m47s
0.8913 (0.00) 0.8049 (0.00) no data
Sparse + BERT + DIET(bow) + ResponseSelector(bow)
test: 2m40s, train: 26m49s, total: 29m28s
0.8699 (-0.00) 0.7504 (0.00) no data
Sparse + BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m56s, train: 19m0s, total: 21m56s
0.8727 (0.00) 0.7994 (0.00) no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 1m6s, train: 21m14s, total: 22m19s
0.8336 (0.00) 0.7504 (0.00) no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 1m21s, train: 14m38s, total: 15m58s
0.8355 (0.00) 0.7561 (0.00) no data

Dataset: Private 1, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m49s, train: 4m1s, total: 5m49s
0.9096 (0.00) 0.9612 (0.00) no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m10s, train: 3m46s, total: 5m56s
0.9148 (0.00) 0.9717 (0.00) no data
Spacy + DIET(bow) + ResponseSelector(bow)
test: 34s, train: 3m2s, total: 3m35s
0.8420 (0.00) 0.9574 (0.00) no data
Spacy + DIET(seq) + ResponseSelector(t2t)
test: 53s, train: 3m25s, total: 4m17s
0.8534 (-0.00) 0.9444 (0.00) no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 29s, train: 3m37s, total: 4m6s
0.8929 (0.00) 0.9612 (0.00) no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 48s, train: 3m32s, total: 4m20s
0.9085 (0.01) 0.9735 (0.00) no data
Sparse + Spacy + DIET(bow) + ResponseSelector(bow)
test: 38s, train: 4m34s, total: 5m11s
0.8960 (0.00) 0.9574 (0.00) no data
Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)
test: 57s, train: 4m21s, total: 5m18s
0.8929 (-0.01) 0.9700 (0.00) no data

Dataset: Private 2, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m50s, train: 11m17s, total: 13m7s
0.8745 (0.00) no data no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 2m5s, train: 6m18s, total: 8m23s
0.8830 (0.00) no data no data
Spacy + DIET(bow) + ResponseSelector(bow)
test: 38s, train: 5m59s, total: 6m36s
0.7253 (-0.00) no data no data
Spacy + DIET(seq) + ResponseSelector(t2t)
test: 47s, train: 6m0s, total: 6m47s
0.7822 (0.00) no data no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 37s, train: 5m41s, total: 6m18s
0.8498 (0.01) no data no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 44s, train: 5m40s, total: 6m24s
0.8530 (-0.00) no data no data
Sparse + Spacy + DIET(bow) + ResponseSelector(bow)
test: 48s, train: 8m35s, total: 9m23s
0.8594 (-0.00) no data no data
Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)
test: 52s, train: 7m16s, total: 8m8s
0.8509 (0.00) no data no data

Dataset: Private 3, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 59s, train: 1m10s, total: 2m8s
0.9177 (0.00) no data no data
BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m4s, train: 52s, total: 1m55s
0.8436 (0.00) no data no data
Spacy + DIET(bow) + ResponseSelector(bow)
test: 36s, train: 54s, total: 1m30s
0.6132 (-0.00) no data no data
Spacy + DIET(seq) + ResponseSelector(t2t)
test: 42s, train: 44s, total: 1m25s
0.6255 (0.00) no data no data
Sparse + DIET(bow) + ResponseSelector(bow)
test: 33s, train: 1m6s, total: 1m38s
0.8683 (0.00) no data no data
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 37s, train: 49s, total: 1m25s
0.8642 (0.00) no data no data
Sparse + Spacy + DIET(bow) + ResponseSelector(bow)
test: 37s, train: 1m18s, total: 1m55s
0.8436 (-0.00) no data no data
Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)
test: 43s, train: 58s, total: 1m40s
0.8601 (0.00) no data no data

Dataset: Sara, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Dialog Policy Configuration Action Level Micro Avg. F1 Conversation Level Accuracy Run Time Train Run Time Test
Rules 0.1266 (0.00) 0.0000 (0.00) 2m34s 1m24s
Rules + AugMemo 0.9149 (0.00) 0.6301 (0.00) 2m30s 1m33s
Rules + AugMemo + TED 0.9727 (-0.00) 0.7534 (-0.00) 13m8s 3m6s
Rules + Memo 0.3860 (-0.11) 0.1438 (-0.03) 2m34s 1m27s
Rules + Memo + TED 0.9555 (-0.00) 0.6644 (-0.00) 13m2s 3m5s

@github-actions
Copy link
Contributor

Hey @wochinge! 👋 To run model regression tests, comment with the /modeltest command and a configuration.

Tips 💡: The model regression test will be run on push events. You can re-run the tests by re-add status:model-regression-tests label or use a Re-run jobs button in Github Actions workflow.

Tips 💡: Every time when you want to change a configuration you should edit the comment with the previous configuration.

You can copy this in your comment and customize:

/modeltest

```yml
##########
## Available datasets
##########
# - "Carbon Bot" (NLU)
# - "Hermit" (NLU)
# - "Private 1" (NLU)
# - "Private 2" (NLU)
# - "Private 3" (NLU)
# - "Sara" (NLU, Core)
# - "financial-demo" (NLU, Core)
# - "helpdesk-assistant" (NLU, Core)
# - "insurance-demo" (NLU, Core)
# - "retail-demo" (NLU, Core)

##########
## Available NLU configurations
##########
# - "BERT + DIET(bow) + ResponseSelector(bow)"
# - "BERT + DIET(seq) + ResponseSelector(t2t)"
# - "Spacy + DIET(bow) + ResponseSelector(bow)"
# - "Spacy + DIET(seq) + ResponseSelector(t2t)"
# - "Sparse + BERT + DIET(bow) + ResponseSelector(bow)"
# - "Sparse + BERT + DIET(seq) + ResponseSelector(t2t)"
# - "Sparse + DIET(bow) + ResponseSelector(bow)"
# - "Sparse + DIET(seq) + ResponseSelector(t2t)"
# - "Sparse + Spacy + DIET(bow) + ResponseSelector(bow)"
# - "Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)"

##########
## Available Core configurations
##########
# - "Rules"
# - "Rules + AugMemo"
# - "Rules + AugMemo + TED"
# - "Rules + Memo"
# - "Rules + Memo + TED"
# - "Rules + TED"

## Example configuration
#################### syntax #################
## include:
##   - dataset: ["<dataset_name>"]
##     config: ["<configuration_name>"]
#
## Example:
## include:
##  - dataset: ["Carbon Bot"]
##    config: ["Sparse + DIET(bow) + ResponseSelector(bow)"]
#
## Shortcut:
## You can use the "all" shortcut to include all available configurations or datasets
#
## Example: Use the "Sparse + EmbeddingIntent + ResponseSelector(bow)" configuration
## for all available datasets
## include:
##  - dataset: ["all"]
##    config: ["Sparse + DIET(bow) + ResponseSelector(bow)"]
#
## Example: Use all available configurations for the "Carbon Bot" and "Sara" datasets
## and for the "Hermit" dataset use the "Sparse + DIET + ResponseSelector(T2T)" and
## "BERT + DIET + ResponseSelector(T2T)" configurations:
## include:
##  - dataset: ["Carbon Bot", "Sara"]
##    config: ["all"]
##  - dataset: ["Hermit"]
##    config: ["Sparse + DIET(seq) + ResponseSelector(t2t)", "BERT + DIET(seq) + ResponseSelector(t2t)"]
#
## Example: Define a branch name to check-out for a dataset repository. Default branch is 'main'
## dataset_branch: "test-branch"
## include:
##  - dataset: ["Carbon Bot", "Sara"]
##    config: ["all"]
##
## Shortcuts:
## You can use the "all" shortcut to include all available configurations or datasets.
## You can use the "all-nlu" shortcut to include all available NLU configurations or datasets.
## You can use the "all-core" shortcut to include all available core configurations or datasets.

include:
 - dataset: ["Carbon Bot"]
   config: ["Sparse + DIET(bow) + ResponseSelector(bow)"]

```

@github-actions
Copy link
Contributor

/modeltest

dataset_branch: "architecture-revamp/modified-spacy-configs"
include:
 - dataset: ["Carbon Bot"]
   config:
   - "BERT + DIET(bow) + ResponseSelector(bow)"
   - "BERT + DIET(seq) + ResponseSelector(t2t)"
   - "Spacy + DIET(bow) + ResponseSelector(bow)"
   - "Spacy + DIET(seq) + ResponseSelector(t2t)"
   - "Sparse + BERT + DIET(bow) + ResponseSelector(bow)"
   - "Sparse + BERT + DIET(seq) + ResponseSelector(t2t)"
   - "Sparse + DIET(bow) + ResponseSelector(bow)"
   - "Sparse + DIET(seq) + ResponseSelector(t2t)"
   - "Sparse + Spacy + DIET(bow) + ResponseSelector(bow)"
   - "Sparse + Spacy + DIET(seq) + ResponseSelector(t2t)"

@github-actions
Copy link
Contributor

The model regression tests have started. It might take a while, please be patient.
As soon as results are ready you'll see a new comment with the results.

Used configuration can be found in the comment.

@github-actions
Copy link
Contributor

Commit: 58cc760, The full report is available as an artifact.

Dataset: Carbon Bot, Dataset repository branch: architecture-revamp/modified-spacy-configs, commit: a88501268464439d1d058a8b77f16a1c752230bd

Configuration Intent Classification Micro F1 Entity Recognition Micro F1 Response Selection Micro F1
BERT + DIET(bow) + ResponseSelector(bow)
test: 1m23s, train: 4m12s, total: 5m34s
0.7942 (0.00) 0.7529 (0.00) 0.5382 (0.00)
BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m42s, train: 4m24s, total: 6m5s
0.8078 (0.00) 0.7787 (0.00) 0.5430 (0.00)
Sparse + BERT + DIET(bow) + ResponseSelector(bow)
test: 1m31s, train: 4m55s, total: 6m25s
0.7883 (0.00) 0.7529 (0.00) 0.5695 (0.00)
Sparse + BERT + DIET(seq) + ResponseSelector(t2t)
test: 1m48s, train: 5m7s, total: 6m55s
0.7806 (0.00) 0.7880 (0.00) 0.5695 (0.00)
Sparse + DIET(bow) + ResponseSelector(bow)
test: 42s, train: 2m47s, total: 3m29s
0.7612 (0.00) 0.7529 (0.00) 0.5316 (0.00)
Sparse + DIET(seq) + ResponseSelector(t2t)
test: 1m0s, train: 4m0s, total: 5m0s
0.7398 (0.00) 0.7022 (0.00) 0.5099 (0.00)

@wochinge wochinge merged commit e2d1e9b into main Oct 14, 2021
@wochinge wochinge deleted the 3.0-architecture-revamp/9277/recipe branch October 14, 2021 19:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
4 participants